Climate Change & Crop Production¶

How is climate change affecting global crop production? I will try to answer this question by using different analysis using the Food and Agriculture Organization of the United Nation (FAO) which can be found here http://www.fao.org/faostat/en/?#data/QC

import Libraries¶

import pandas as pd
import numpy as np
import seaborn as sns 
import matplotlib.pyplot as plt
%matplotlib inline
# Suppress warnings from pandas
import warnings
warnings.filterwarnings('ignore')
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn import metrics
from sklearn.metrics import precision_score ,recall_score, f1_score
from sklearn.metrics import accuracy_score

import chart_studio
username = 'omegamarkos' # your username
api_key = 'PUk2JYOCBrghPN2lfAay' # your api key - go to profile > settings > regenerate key
chart_studio.tools.set_credentials_file(username=username, api_key=api_key)

from plotly.offline import iplot, init_notebook_mode,download_plotlyjs
import plotly.graph_objects as go
import plotly.express as px

#use this code to be able to display all the output in the cell instead of only displaying the out put for the last one. see the next cell.
from IPython.core.interactiveshell import InteractiveShell  
InteractiveShell.ast_node_interactivity = "all"

Crop Production Visualization¶

df_prod=pd.read_csv('FAOSTAT_crop_production.csv') # Total yearly crop production in tonnes by country

df_prod.head()

df_prod['Item'] = df_prod['Item'].str.replace('Rice, paddy', 'Rice') # rename the the item name rice to make it easier to access

df_prod.rename(columns={'Value':'prod'}, inplace=True) # rename the column value to prod to avoid confusion for later

df_prod.Area.unique()

array(['Afghanistan', 'Albania', 'Algeria', 'Angola',
       'Antigua and Barbuda', 'Argentina', 'Armenia', 'Australia',
       'Austria', 'Azerbaijan', 'Bahamas', 'Bangladesh', 'Barbados',
       'Belarus', 'Belgium', 'Belgium-Luxembourg', 'Belize', 'Benin',
       'Bhutan', 'Bolivia (Plurinational State of)',
       'Bosnia and Herzegovina', 'Botswana', 'Brazil',
       'Brunei Darussalam', 'Bulgaria', 'Burkina Faso', 'Burundi',
       'Cabo Verde', 'Cambodia', 'Cameroon', 'Canada',
       'Central African Republic', 'Chad', 'Chile', 'China',
       'China, Hong Kong SAR', 'China, mainland',
       'China, Taiwan Province of', 'Colombia', 'Comoros', 'Congo',
       'Costa Rica', "Côte d'Ivoire", 'Croatia', 'Cuba', 'Cyprus',
       'Czechia', 'Czechoslovakia',
       "Democratic People's Republic of Korea",
       'Democratic Republic of the Congo', 'Denmark', 'Djibouti',
       'Dominica', 'Dominican Republic', 'Ecuador', 'Egypt',
       'El Salvador', 'Eritrea', 'Estonia', 'Eswatini', 'Ethiopia',
       'Ethiopia PDR', 'Fiji', 'Finland', 'France', 'French Guiana',
       'Gabon', 'Gambia', 'Georgia', 'Germany', 'Ghana', 'Greece',
       'Grenada', 'Guadeloupe', 'Guam', 'Guatemala', 'Guinea',
       'Guinea-Bissau', 'Guyana', 'Haiti', 'Honduras', 'Hungary',
       'Iceland', 'India', 'Indonesia', 'Iran (Islamic Republic of)',
       'Iraq', 'Ireland', 'Israel', 'Italy', 'Jamaica', 'Japan', 'Jordan',
       'Kazakhstan', 'Kenya', 'Kuwait', 'Kyrgyzstan',
       "Lao People's Democratic Republic", 'Latvia', 'Lebanon', 'Lesotho',
       'Liberia', 'Libya', 'Lithuania', 'Luxembourg', 'Madagascar',
       'Malawi', 'Malaysia', 'Maldives', 'Mali', 'Malta', 'Mauritania',
       'Mauritius', 'Mexico', 'Micronesia (Federated States of)',
       'Mongolia', 'Montenegro', 'Montserrat', 'Morocco', 'Mozambique',
       'Myanmar', 'Namibia', 'Nepal', 'Netherlands', 'New Caledonia',
       'New Zealand', 'Nicaragua', 'Niger', 'Nigeria', 'North Macedonia',
       'Norway', 'Oman', 'Pacific Islands Trust Territory', 'Pakistan',
       'Palestine', 'Panama', 'Papua New Guinea', 'Paraguay', 'Peru',
       'Philippines', 'Poland', 'Portugal', 'Puerto Rico', 'Qatar',
       'Republic of Korea', 'Republic of Moldova', 'Réunion', 'Romania',
       'Russian Federation', 'Rwanda', 'Saint Lucia',
       'Saint Vincent and the Grenadines', 'Sao Tome and Principe',
       'Saudi Arabia', 'Senegal', 'Serbia', 'Serbia and Montenegro',
       'Sierra Leone', 'Slovakia', 'Slovenia', 'Solomon Islands',
       'Somalia', 'South Africa', 'South Sudan', 'Spain', 'Sri Lanka',
       'Sudan', 'Sudan (former)', 'Suriname', 'Sweden', 'Switzerland',
       'Syrian Arab Republic', 'Tajikistan', 'Thailand', 'Timor-Leste',
       'Togo', 'Trinidad and Tobago', 'Tunisia', 'Turkey', 'Turkmenistan',
       'Uganda', 'Ukraine', 'United Arab Emirates', 'United Kingdom',
       'United Republic of Tanzania', 'United States of America',
       'Uruguay', 'USSR', 'Uzbekistan', 'Vanuatu',
       'Venezuela (Bolivarian Republic of)', 'Viet Nam', 'Western Sahara',
       'Yemen', 'Yugoslav SFR', 'Zambia', 'Zimbabwe'], dtype=object)

Who produces the most ?¶

df_prod_2018 = df_prod.query("Year == 2018")
df_prod_2018_wheat =df_prod_2018.query("Item == 'Wheat'")
df_prod_2018_wheat_top =df_prod_2018_wheat.nlargest(10,['prod'])
df_prod_2018_wheat_top.head()

fig = px.bar(df_prod_2018_wheat_top, y='prod', x='Area', text='prod').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide',title ='Top Wheat Producers')
fig.show()

#To open the plot on chart studio web
import chart_studio.plotly as py
py.plot(fig, filename = 'wheat producers', auto_open=True)

'https://plotly.com/~omegamarkos/1/'

The top wheat producing countries are China, India & Russia¶

df_prod_2018_rice =df_prod_2018.query("Item == 'Rice'") # only rice data
df_prod_2018_rice_top =df_prod_2018_rice.nlargest(10,['prod']) #the top 10

fig = px.bar(df_prod_2018_rice_top, y='prod', x='Area', text='prod').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide', title ='Top Rice Producers')
fig.show()

The top rice producing countries are China, India & Indonesia¶

df_prod_2018_maize =df_prod_2018.query("Item == 'Maize'")
df_prod_2018_maize_top =df_prod_2018_maize.nlargest(10,['prod'])

fig = px.bar(df_prod_2018_maize_top, y='prod', x='Area', text='prod').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide',title ='Top Maize Producers')
fig.show()

# fig = px.bar(df_prod_rice, x="Area", y= "prod").update_xaxes(categoryorder="max descending")
# fig.show()

fig =  px.choropleth(df_prod,locations="Area", locationmode="country names",animation_frame="Year", animation_group="Area",
            color="prod",color_continuous_scale= 'YlGn' , hover_name="Area", title = 'Total crop production by Country').update_geos(
    resolution=50,
    showcoastlines=True, coastlinecolor="RebeccaPurple",
    showland=True, landcolor="LightGreen",
    showocean=True, oceancolor="LightBlue",
    showlakes=True, lakecolor="Blue",
    showrivers=True, rivercolor="Blue"
)
fig.show()

Crop yield per hectare Visualization¶

df_crop =pd.read_csv('FAOSTAT_data_main_crop_yield.csv') # crop yield per hectare

df_crop.head()

from pandas_profiling import ProfileReport
crop_profile = ProfileReport(df_crop)
crop_profile

# drop the missing values
df_crop= df_crop.dropna()

df_crop.columns

Index(['Domain Code', 'Domain', 'Area Code', 'Area', 'Element Code', 'Element',
       'Item Code', 'Item', 'Year Code', 'Year', 'Unit', 'Value', 'Flag',
       'Flag Description'],
      dtype='object')

#change name to avoid confusion
df_crop.rename(columns={'Value':'yield'}, inplace=True)

df_crop.columns

Index(['Domain Code', 'Domain', 'Area Code', 'Area', 'Element Code', 'Element',
       'Item Code', 'Item', 'Year Code', 'Year', 'Unit', 'yield', 'Flag',
       'Flag Description'],
      dtype='object')

We only need the following features from the data. the rest are either constant or irrelevant
[ 'Area Code', 'Area','Item Code', 'Item', 'Year', 'Value']

df_crop = df_crop[['Area Code', 'Area','Item Code', 'Item', 'Year', 'yield']]
df_crop.tail()

# def getFiltered(df,col):
#     df_sub=df.query("Item = {}".format(col))
#     df_sub_max = df_sub.groupby(['Year'], as_index = False)['Value'].max()
#     return df_sub_max

df_crop['Item'] = df_crop['Item'].str.replace('Rice, paddy', 'Rice')

df_crop['Item'].unique()

array(['Barley', 'Maize', 'Millet', 'Rice', 'Wheat', 'Sorghum'],
      dtype=object)

Do the top producing countries also have high yield?¶

df_crop_2018 = df_crop.query("Year == 2018")
df_crop_2018_rice =df_crop_2018.query("Item == 'Rice'") # only rice data
df_crop_2018_rice_top =df_crop_2018_rice.nlargest(10,['yield']) #the top 10
df_crop_2018_rice_top.head()

fig = px.pie(df_crop_2018_rice_top, values='yield', names='Area',
             title='top high rice yield ',
             hover_data=['yield'], labels={'yield':' crop yield'}).update_traces(textposition='inside', textinfo='percent+label')
fig.show()

fig = px.bar(df_crop_2018_rice_top, y='yield', x='Area', text='yield').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide',title ='Top Rice Yield')
fig.show()

df_crop_2018_wheat =df_crop_2018.query("Item == 'Wheat'") # only rice data
df_crop_2018_wheat_top =df_crop_2018_wheat.nlargest(10,['yield'])

fig = px.bar(df_crop_2018_wheat_top, y='yield', x='Area', text='yield').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide',title ='Top Wheat Yield')
fig.show()

df_crop_2018_maize =df_crop_2018.query("Item == 'Maize'") # only rice data
df_crop_2018_maize_top =df_crop_2018_maize.nlargest(10,['yield'])

fig = px.bar(df_crop_2018_maize_top, y='yield', x='Area', text='yield').update_traces(texttemplate='%{text:.2s}', textposition='outside').update_layout(uniformtext_minsize=8, uniformtext_mode='hide',title ='Top Maize Yield')
fig.show()

Crop & Region merged¶

df_reg =pd.read_csv('regional_code.csv') #  regions for the country data

df_reg.head()

df_region = df_reg[['Country Group','Country Code']]
df_region.head()

df_region.isna().sum()

Country Group    0
Country Code     0
dtype: int64

df_crop.head()

df_crop_reg = pd.merge(df_crop, df_region, how='left', left_on=['Area Code'], right_on=['Country Code'])
df_crop_reg.head()

# df_crop_reg_profile = ProfileReport(df_crop_reg)
# df_crop_reg_profile

df_crop_reg = df_crop_reg.dropna()

df_crop_reg_2017 = df_crop_reg.query("Year =='2017'")

Map with folium¶

import folium

url = 'https://raw.githubusercontent.com/python-visualization/folium/master/examples/data'
country_shapes = f'{url}/world-countries.json'
the_map = folium.Map()
the_map.choropleth(
    geo_data=country_shapes,
    name='choropleth',
    data=df_crop_reg_2017,
    columns=['Area', 'yield'],
    key_on='feature.properties.name',
    fill_color='Reds',
    nan_fill_color='white',
    fill_opacity=0.7,
    line_opacity=0.2,
)
folium.LayerControl().add_to(the_map)
the_map

<folium.map.LayerControl at 0x259bfb0c160>

df_crop_reg_2017_m = df_crop_reg_2017.query("Item =='Maize'")

url = 'https://raw.githubusercontent.com/python-visualization/folium/master/examples/data'
country_shapes = f'{url}/world-countries.json'
maize_map = folium.Map()
maize_map.choropleth(
    geo_data=country_shapes,
    name='choropleth',
    data=df_crop_reg_2017_m,
    columns=['Area', 'yield'],
    key_on='feature.properties.name',
    fill_color='Reds',
    nan_fill_color='white',
    fill_opacity=0.7,
    line_opacity=0.2,
)
folium.LayerControl().add_to(maize_map)
maize_map

<folium.map.LayerControl at 0x259c3c80c50>

Temperature anomaly visualization¶

df_temp = pd.read_csv('global_temp_change.csv')

df_temp.head()

#df_temp.Area.unique()

df_temp.columns

Index(['Domain Code', 'Domain', 'Area Code', 'Area', 'Element Code', 'Element',
       'Months Code', 'Months', 'Year Code', 'Year', 'Unit', 'Value', 'Flag',
       'Flag Description'],
      dtype='object')

df_temp.rename(columns={'Value':'temperature'}, inplace =True)

df_temp.columns

Index(['Domain Code', 'Domain', 'Area Code', 'Area', 'Element Code', 'Element',
       'Months Code', 'Months', 'Year Code', 'Year', 'Unit', 'temperature',
       'Flag', 'Flag Description'],
      dtype='object')

We only need the following features from the data. the rest are either constant or irrelevant
[ 'Area Code', 'Area','Months Code', 'Months', 'Year', 'Value']

df_temp = df_temp[[ 'Area Code', 'Area','Months Code', 'Months', 'Year', 'temperature']]
df_temp.head()

df_temp.isna().sum()

Area Code         0
Area              0
Months Code       0
Months            0
Year              0
temperature    7685
dtype: int64

df_temp=df_temp.dropna()

df_temp.Area.unique()

array(['Afghanistan', 'Albania', 'Algeria', 'American Samoa', 'Andorra',
       'Angola', 'Anguilla', 'Antarctica', 'Antigua and Barbuda',
       'Argentina', 'Armenia', 'Aruba', 'Australia', 'Austria',
       'Azerbaijan', 'Bahamas', 'Bahrain', 'Bangladesh', 'Barbados',
       'Belarus', 'Belgium', 'Belgium-Luxembourg', 'Belize', 'Benin',
       'Bhutan', 'Bolivia (Plurinational State of)',
       'Bosnia and Herzegovina', 'Botswana', 'Brazil',
       'British Virgin Islands', 'Brunei Darussalam', 'Bulgaria',
       'Burkina Faso', 'Burundi', 'Cabo Verde', 'Cambodia', 'Cameroon',
       'Canada', 'Cayman Islands', 'Central African Republic', 'Chad',
       'Channel Islands', 'Chile', 'China', 'China, Hong Kong SAR',
       'China, Macao SAR', 'China, mainland', 'China, Taiwan Province of',
       'Christmas Island', 'Cocos (Keeling) Islands', 'Colombia',
       'Comoros', 'Congo', 'Cook Islands', 'Costa Rica', "Côte d'Ivoire",
       'Croatia', 'Cuba', 'Cyprus', 'Czechia', 'Czechoslovakia',
       "Democratic People's Republic of Korea",
       'Democratic Republic of the Congo', 'Denmark', 'Djibouti',
       'Dominica', 'Dominican Republic', 'Ecuador', 'Egypt',
       'El Salvador', 'Equatorial Guinea', 'Eritrea', 'Estonia',
       'Eswatini', 'Ethiopia', 'Ethiopia PDR',
       'Falkland Islands (Malvinas)', 'Faroe Islands', 'Fiji', 'Finland',
       'France', 'French Guiana', 'French Polynesia',
       'French Southern and Antarctic Territories', 'Gabon', 'Gambia',
       'Georgia', 'Germany', 'Ghana', 'Gibraltar', 'Greece', 'Greenland',
       'Grenada', 'Guadeloupe', 'Guatemala', 'Guinea', 'Guinea-Bissau',
       'Guyana', 'Haiti', 'Holy See', 'Honduras', 'Hungary', 'Iceland',
       'India', 'Indonesia', 'Iran (Islamic Republic of)', 'Iraq',
       'Ireland', 'Isle of Man', 'Israel', 'Italy', 'Jamaica', 'Japan',
       'Jordan', 'Kazakhstan', 'Kenya', 'Kiribati', 'Kuwait',
       'Kyrgyzstan', "Lao People's Democratic Republic", 'Latvia',
       'Lebanon', 'Lesotho', 'Liberia', 'Libya', 'Liechtenstein',
       'Lithuania', 'Luxembourg', 'Madagascar', 'Malawi', 'Malaysia',
       'Maldives', 'Mali', 'Malta', 'Marshall Islands', 'Martinique',
       'Mauritania', 'Mauritius', 'Mayotte', 'Mexico',
       'Micronesia (Federated States of)', 'Midway Island', 'Monaco',
       'Mongolia', 'Montenegro', 'Montserrat', 'Morocco', 'Mozambique',
       'Myanmar', 'Namibia', 'Nauru', 'Nepal', 'Netherlands',
       'Netherlands Antilles (former)', 'New Caledonia', 'New Zealand',
       'Nicaragua', 'Niger', 'Nigeria', 'Niue', 'Norfolk Island',
       'North Macedonia', 'Norway', 'Oman',
       'Pacific Islands Trust Territory', 'Pakistan', 'Palau',
       'Palestine', 'Panama', 'Papua New Guinea', 'Paraguay', 'Peru',
       'Philippines', 'Pitcairn Islands', 'Poland', 'Portugal',
       'Puerto Rico', 'Qatar', 'Republic of Korea', 'Republic of Moldova',
       'Réunion', 'Romania', 'Russian Federation', 'Rwanda',
       'Saint Helena, Ascension and Tristan da Cunha',
       'Saint Kitts and Nevis', 'Saint Lucia',
       'Saint Pierre and Miquelon', 'Saint Vincent and the Grenadines',
       'Samoa', 'San Marino', 'Sao Tome and Principe', 'Saudi Arabia',
       'Senegal', 'Serbia', 'Serbia and Montenegro', 'Seychelles',
       'Sierra Leone', 'Singapore', 'Slovakia', 'Slovenia',
       'Solomon Islands', 'Somalia', 'South Africa',
       'South Georgia and the South Sandwich Islands', 'South Sudan',
       'Spain', 'Sri Lanka', 'Sudan', 'Sudan (former)', 'Suriname',
       'Svalbard and Jan Mayen Islands', 'Sweden', 'Switzerland',
       'Syrian Arab Republic', 'Tajikistan', 'Thailand', 'Timor-Leste',
       'Togo', 'Tokelau', 'Tonga', 'Trinidad and Tobago', 'Tunisia',
       'Turkey', 'Turkmenistan', 'Turks and Caicos Islands', 'Tuvalu',
       'Uganda', 'Ukraine', 'United Arab Emirates', 'United Kingdom',
       'United Republic of Tanzania', 'United States of America',
       'United States Virgin Islands', 'Uruguay', 'USSR', 'Uzbekistan',
       'Vanuatu', 'Venezuela (Bolivarian Republic of)', 'Viet Nam',
       'Wake Island', 'Wallis and Futuna Islands', 'Western Sahara',
       'Yemen', 'Yugoslav SFR', 'Zambia', 'Zimbabwe'], dtype=object)

# create a positive anomaly column bc the animation doesn't work for negative values
df_temp['pos_temp'] = df_temp.temperature.apply(lambda x: 0 if x < 0  else x)
df_temp.head()

# taking only the yearly anomaly 
df_temp_metro = df_temp.query("Months == 'Meteorological year'") 
df_temp_metro.head()

#sortthe highest 20 anomalies 
df_temp_top_20 = df_temp_metro.nlargest(20,['temperature'])
df_temp_top_20

#plot the highest 20 anomaly
fig = px.scatter(df_temp_top_20, x="Year", y="temperature", size='temperature' ,title='Highest Temperature Anomaly since 1960')
fig.show()

The highest 20 temperature anomaly are after the year 2000. The year 2016 being the highest¶

# Animation by year
fig =  px.choropleth(df_temp_metro,locations="Area", locationmode="country names",animation_frame="Year", animation_group="Area",
            color="pos_temp",color_continuous_scale= 'reds' , hover_name="Area", title = 'Global Temperature Anomaly')

fig.show()

import plotly.io as pio
pio.write_html(fig, file='temp.html', auto_open=True)

Carbon dioxide(Co2) emission visualization¶

df_co2_all = pd.read_csv('WorldCo2TotalWorldBank.csv')

df_co2_all.head()

# Melt data from wide format to long format 
df_co2 = pd.melt(df_co2_all, id_vars=['Country Name','Country Code' ,'Indicator Name', 'Indicator Code'], var_name='year',value_name='Value')
df_co2.head()

df_co2.isna().sum()

Country Name        0
Country Code        0
Indicator Name      0
Indicator Code      0
year                0
Value             339
dtype: int64

#Fill the missing values using forward fill method
df_co2.fillna(method='ffill', inplace = True)

df_co2.isna().sum()

Country Name        0
Country Code        0
Indicator Name      0
Indicator Code      0
year                0
Value             339
dtype: int64

df_co2= df_co2.drop(['Indicator Name','Indicator Code'], axis = 1)
df_co2.head()

df_co2.rename (columns={'Country Name':'CountryName','Country Code':'CountryCode', 'Value':'co2'}, inplace= True)

df_co2['CountryName'].unique()

array(['Aruba', 'Afghanistan', 'Angola', 'Albania', 'Arab World',
       'United Arab Emirates', 'Argentina', 'Armenia', 'American Samoa',
       'Australia', 'Austria', 'Azerbaijan', 'Burundi', 'Belgium',
       'Benin', 'Burkina Faso', 'Bangladesh', 'Bulgaria', 'Bahrain',
       'Bahamas, The', 'Bosnia and Herzegovina', 'Belarus', 'Belize',
       'Bermuda', 'Bolivia', 'Brazil', 'Barbados', 'Brunei Darussalam',
       'Bhutan', 'Botswana', 'Central African Republic', 'Canada',
       'Central Europe and the Baltics', 'Switzerland', 'Chile', 'China',
       "Cote d'Ivoire", 'Cameroon', 'Congo, Dem. Rep.', 'Congo, Rep.',
       'Colombia', 'Comoros', 'Cabo Verde', 'Costa Rica',
       'Caribbean small states', 'Cuba', 'Cayman Islands', 'Cyprus',
       'Czech Republic', 'Germany', 'Djibouti', 'Dominica', 'Denmark',
       'Dominican Republic', 'Algeria',
       'East Asia & Pacific (excluding high income)',
       'Early-demographic dividend', 'East Asia & Pacific',
       'Europe & Central Asia (excluding high income)',
       'Europe & Central Asia', 'Ecuador', 'Egypt, Arab Rep.',
       'Euro area', 'Eritrea', 'Spain', 'Estonia', 'Ethiopia',
       'European Union', 'Fragile and conflict affected situations',
       'Finland', 'Fiji', 'France', 'Micronesia, Fed. Sts.', 'Gabon',
       'United Kingdom', 'Georgia', 'Ghana', 'Guinea', 'Gambia, The',
       'Guinea-Bissau', 'Equatorial Guinea', 'Greece', 'Grenada',
       'Guatemala', 'Guam', 'Guyana', 'High income',
       'Hong Kong SAR, China', 'Honduras',
       'Heavily indebted poor countries (HIPC)', 'Croatia', 'Haiti',
       'Hungary', 'IBRD only', 'IDA & IBRD total', 'IDA total',
       'IDA blend', 'Indonesia', 'IDA only', 'India', 'Ireland',
       'Iran, Islamic Rep.', 'Iraq', 'Iceland', 'Israel', 'Italy',
       'Jamaica', 'Jordan', 'Japan', 'Kazakhstan', 'Kenya',
       'Kyrgyz Republic', 'Cambodia', 'St. Kitts and Nevis',
       'Korea, Rep.', 'Kuwait',
       'Latin America & Caribbean (excluding high income)', 'Lao PDR',
       'Lebanon', 'Liberia', 'Libya', 'St. Lucia',
       'Latin America & Caribbean',
       'Least developed countries: UN classification', 'Low income',
       'Sri Lanka', 'Lower middle income', 'Low & middle income',
       'Lesotho', 'Late-demographic dividend', 'Lithuania', 'Luxembourg',
       'Latvia', 'Macao SAR, China', 'Morocco', 'Moldova', 'Madagascar',
       'Maldives', 'Middle East & North Africa', 'Mexico',
       'Marshall Islands', 'Middle income', 'North Macedonia', 'Mali',
       'Malta', 'Myanmar',
       'Middle East & North Africa (excluding high income)', 'Mongolia',
       'Northern Mariana Islands', 'Mozambique', 'Mauritania',
       'Mauritius', 'Malawi', 'Malaysia', 'North America', 'Namibia',
       'Niger', 'Nigeria', 'Nicaragua', 'Netherlands', 'Norway', 'Nepal',
       'New Zealand', 'OECD members', 'Oman', 'Other small states',
       'Pakistan', 'Panama', 'Peru', 'Philippines', 'Papua New Guinea',
       'Poland', 'Pre-demographic dividend', 'Puerto Rico',
       'Korea, Dem. People’s Rep.', 'Portugal', 'Paraguay',
       'Pacific island small states', 'Post-demographic dividend',
       'Qatar', 'Romania', 'Russian Federation', 'Rwanda', 'South Asia',
       'Saudi Arabia', 'Sudan', 'Senegal', 'Solomon Islands',
       'Sierra Leone', 'El Salvador', 'Somalia',
       'Sub-Saharan Africa (excluding high income)', 'Sub-Saharan Africa',
       'Small states', 'Sao Tome and Principe', 'Suriname',
       'Slovak Republic', 'Slovenia', 'Sweden', 'Eswatini', 'Seychelles',
       'Syrian Arab Republic', 'Turks and Caicos Islands', 'Chad',
       'East Asia & Pacific (IDA & IBRD countries)',
       'Europe & Central Asia (IDA & IBRD countries)', 'Togo', 'Thailand',
       'Tajikistan', 'Turkmenistan',
       'Latin America & the Caribbean (IDA & IBRD countries)',
       'Timor-Leste', 'Middle East & North Africa (IDA & IBRD countries)',
       'Tonga', 'South Asia (IDA & IBRD)',
       'Sub-Saharan Africa (IDA & IBRD countries)', 'Tunisia', 'Turkey',
       'Tuvalu', 'Tanzania', 'Uganda', 'Ukraine', 'Upper middle income',
       'Uruguay', 'United States', 'Uzbekistan',
       'St. Vincent and the Grenadines', 'Venezuela, RB',
       'British Virgin Islands', 'Virgin Islands (U.S.)', 'Vietnam',
       'Vanuatu', 'World', 'Samoa', 'Yemen, Rep.', 'South Africa',
       'Zambia', 'Zimbabwe'], dtype=object)

df_temp_metro.head()

df_temp_metro_world_max = df_temp_metro.groupby(['Year'], as_index=False)['temperature'].max()
df_temp_metro_world_max.tail()

df_co2_world = df_co2.query("CountryName == 'World'")
df_co2_world.head()

df_co2_world.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 43 entries, 232 to 10228
Data columns (total 4 columns):
CountryName    43 non-null object
CountryCode    43 non-null object
year           43 non-null object
co2            43 non-null float64
dtypes: float64(1), object(3)
memory usage: 1.7+ KB

df_temp_metro_world_max.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 59 entries, 0 to 58
Data columns (total 2 columns):
Year           59 non-null int64
temperature    59 non-null float64
dtypes: float64(1), int64(1)
memory usage: 1.4 KB

df_temp_metro_world_max['Year']=df_temp_metro_world_max['Year'].astype(str)

df_temp_co2 = pd.merge(df_temp_metro_world_max, df_co2_world, how='left', left_on=['Year'], right_on=['year'])
df_temp_co2.head()

df_temp_co2.dropna(inplace= True)
df_temp_co2.head()

import plotly.express as px

fig = px.bar(df_temp_co2, x='Year', y='co2',
             hover_data=['co2', 'temperature'], color='temperature', title= 'Global Co2 Emission & Temperature Anomaly', 
             labels={'co2':'World co2 emission'}, height=400)
fig.show()
py.plot(fig, filename = 'Co2ByTemperature', auto_open=True)

'https://plotly.com/~omegamarkos/3/'

when the Co2 emission gets higher the earth gets warmer¶

fig = go.Figure()
trace = go.Scatter(x=df_co2_world["year"], y=df_co2["co2"], mode="lines+markers")
fig.add_trace(trace)

fig.update_layout(
    title={
        "text": "World Co2 Emission",
        "x":0.5,
        "xanchor": "center"
        },
    xaxis_title="Year",
    yaxis_title="co2 emission")
fig.show()

Merging the Temp & crop¶

df_crop_reg_sorted=df_crop_reg.sort_values(by=['Year'])
df_temp_sorted=df_temp.sort_values(by=['Year'])

df_crop_temp  = pd.merge_asof(df_temp_sorted, df_crop_reg_sorted,
              on='Year',
              by='Area')

df_crop_temp.head()

df_crop_reg.head()

df_crop_temp.isna().sum()

Area Code_x          0
Area                 0
Months Code          0
Months               0
Year                 0
temperature          0
pos_temp             0
Area Code_y      48500
Item Code        48500
Item             48500
yield            48500
Country Group    48500
Country Code     48500
dtype: int64

df_crop_temp= df_crop_temp.dropna()

df_crop_temp.shape

(169677, 13)

df_crop_temp.isna().sum()

Area Code_x      0
Area             0
Months Code      0
Months           0
Year             0
temperature      0
pos_temp         0
Area Code_y      0
Item Code        0
Item             0
yield            0
Country Group    0
Country Code     0
dtype: int64

df_crop_temp.head()

df_crop_temp.Months.unique()

array(['January', 'May', 'June', 'July', 'August', 'September', 'October',
       'November', 'Sep–Oct–Nov', 'December', 'Jun–Jul–Aug',
       'Dec–Jan–Feb', 'Mar–Apr–May', 'Meteorological year', 'April',
       'March', 'February'], dtype=object)

df_crop_temp['temp']= df_crop_temp.temperature.apply(lambda x : 'low' if (x>=0 and x<=2) else 'high')     
df_crop_temp.head()

df_crop_temp_re = df_crop_temp.groupby(['temp']).agg({'yield':'sum'}).reset_index()
df_crop_temp_re.head()

Plot by crop type¶

product =df_crop_temp['Item'].unique()
for prod in product:
     globals()[prod] = df_crop_temp.loc[df_crop_temp['Item'] == prod]

Maize_max =Maize.groupby(['Year'], as_index = False)['yield'].max()
Wheat_max =Wheat.groupby(['Year'], as_index = False)['yield'].max()
Rice_max =Rice.groupby(['Year'], as_index = False)['yield'].max()

import plotly.graph_objects as go
fig = go.Figure()
trace1 = go.Scatter(x=Wheat_max["Year"], y=Wheat_max["yield"], mode="lines+markers", name="Max Wheat")
fig.add_trace(trace1)
trace2 = go.Scatter(x=Rice_max["Year"], y=Rice_max["yield"], mode="lines+markers", name="Max Rice")
fig.add_trace(trace2)
trace3 = go.Scatter(x=Maize_max["Year"], y=Maize_max["yield"], mode="lines+markers", name="Max Maize")
fig.add_trace(trace3)
fig.update_layout(
    title={
        "text": "Wheat, Rice & Maize Maximumy yearly Production",
        "x":0.5,
        "xanchor": "center"
        },
    xaxis_title="Year",
    yaxis_title="Yield per Hectare")
fig.show()

df_crop_temp.rename(columns={"Country Group": "region"} , inplace = True)
df_crop_temp['region'].unique()

array(['Southern Asia', 'World', 'Land Locked Developing Countries',
       'Americas', 'Sub-Saharan Africa (including Sudan)',
       'Net Food Importing Developing Countries', 'Sub-Saharan Africa',
       'Non-Annex I countries', 'Africa', 'Least Developed Countries',
       'Asia', 'Eastern Asia and South-eastern Asia',
       'Low Income Food Deficit Countries', 'Eastern Africa',
       'Latin America and the Caribbean', 'Annex I countries', 'OECD',
       'High-income economies', 'Europe', 'Lower-middle-income economies',
       'South America', 'Western Europe',
       'Small Island Developing States', 'Western Africa',
       'Northern America and Europe', 'Western Asia and Northern Africa',
       'Upper-middle-income economies', 'Caribbean',
       'Oceania excluding Australia and New Zealand', 'Northern Africa',
       'Central America', 'Northern Europe', 'Oceania',
       'Central Asia and Southern Asia', 'Western Asia',
       'Southern Europe', 'Southern Africa', 'European Union',
       'Eastern Asia', 'East Asia (exc China)', 'Middle Africa',
       'South Asia (exc India)', 'North Africa (exc Sudan)',
       'Low income economies', 'South-Eastern Asia', 'Melanesia',
       'Eastern Europe', 'Micronesia', 'Australia and New Zealand',
       'Northern America', 'Central Asia'], dtype=object)

df_crop_temp['region'] = df_crop_temp['region'].str.replace(' ','_')
df_crop_temp['region'].unique()

array(['Southern_Asia', 'World', 'Land_Locked_Developing_Countries',
       'Americas', 'Sub-Saharan_Africa_(including_Sudan)',
       'Net_Food_Importing_Developing_Countries', 'Sub-Saharan_Africa',
       'Non-Annex_I_countries', 'Africa', 'Least_Developed_Countries',
       'Asia', 'Eastern_Asia_and_South-eastern_Asia',
       'Low_Income_Food_Deficit_Countries', 'Eastern_Africa',
       'Latin_America_and_the_Caribbean', 'Annex_I_countries', 'OECD',
       'High-income_economies', 'Europe', 'Lower-middle-income_economies',
       'South_America', 'Western_Europe',
       'Small_Island_Developing_States', 'Western_Africa',
       'Northern_America_and_Europe', 'Western_Asia_and_Northern_Africa',
       'Upper-middle-income_economies', 'Caribbean',
       'Oceania_excluding_Australia_and_New_Zealand', 'Northern_Africa',
       'Central_America', 'Northern_Europe', 'Oceania',
       'Central_Asia_and_Southern_Asia', 'Western_Asia',
       'Southern_Europe', 'Southern_Africa', 'European_Union',
       'Eastern_Asia', 'East_Asia_(exc_China)', 'Middle_Africa',
       'South_Asia_(exc_India)', 'North_Africa_(exc_Sudan)',
       'Low_income_economies', 'South-Eastern_Asia', 'Melanesia',
       'Eastern_Europe', 'Micronesia', 'Australia_and_New_Zealand',
       'Northern_America', 'Central_Asia'], dtype=object)

df_crop_temp['region'] = df_crop_temp['region'].str.replace('-','_')
df_crop_temp['region'].unique()

array(['Southern_Asia', 'World', 'Land_Locked_Developing_Countries',
       'Americas', 'Sub_Saharan_Africa_(including_Sudan)',
       'Net_Food_Importing_Developing_Countries', 'Sub_Saharan_Africa',
       'Non_Annex_I_countries', 'Africa', 'Least_Developed_Countries',
       'Asia', 'Eastern_Asia_and_South_eastern_Asia',
       'Low_Income_Food_Deficit_Countries', 'Eastern_Africa',
       'Latin_America_and_the_Caribbean', 'Annex_I_countries', 'OECD',
       'High_income_economies', 'Europe', 'Lower_middle_income_economies',
       'South_America', 'Western_Europe',
       'Small_Island_Developing_States', 'Western_Africa',
       'Northern_America_and_Europe', 'Western_Asia_and_Northern_Africa',
       'Upper_middle_income_economies', 'Caribbean',
       'Oceania_excluding_Australia_and_New_Zealand', 'Northern_Africa',
       'Central_America', 'Northern_Europe', 'Oceania',
       'Central_Asia_and_Southern_Asia', 'Western_Asia',
       'Southern_Europe', 'Southern_Africa', 'European_Union',
       'Eastern_Asia', 'East_Asia_(exc_China)', 'Middle_Africa',
       'South_Asia_(exc_India)', 'North_Africa_(exc_Sudan)',
       'Low_income_economies', 'South_Eastern_Asia', 'Melanesia',
       'Eastern_Europe', 'Micronesia', 'Australia_and_New_Zealand',
       'Northern_America', 'Central_Asia'], dtype=object)

regions =df_crop_temp['region'].unique()
for reg in regions:
     globals()[reg] = df_crop_temp.loc[df_crop_temp['region'] == reg]

Africa.head()

Africa_maize = Africa.query("Item=='Maize'")
Africa_maize_ave = Africa_maize.groupby(['Year'], as_index=False)['yield'].mean()
Africa_rice = Africa.query("Item=='Rice'")
Africa_rice_ave = Africa_rice.groupby(['Year'], as_index=False)['yield'].mean()
Africa_wheat = Africa.query("Item=='Wheat'")
Africa_wheat_ave = Africa_wheat.groupby(['Year'], as_index=False)['yield'].mean()

fig = go.Figure()
trace1 = go.Scatter(x=Africa_wheat_ave["Year"], y=Africa_wheat_max["yield"], mode="lines+markers", name="Africa Wheat")
fig.add_trace(trace1)
trace2 = go.Scatter(x=Africa_rice_ave["Year"], y=Africa_rice_max["yield"], mode="lines+markers", name="Africa Rice")
fig.add_trace(trace2)
trace3 = go.Scatter(x=Africa_maize_ave["Year"], y=Africa_maize_max["yield"], mode="lines+markers", name="Africa Maize")
fig.add_trace(trace3)
fig.update_layout(
    title={
        "text": "Average Yearly Crop Production in Africa",
        "x":0.5,
        "xanchor": "center"
        },
    xaxis_title="Year",
    yaxis_title="Yield per Hectare")
fig.show()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-109-c0a156dd8573> in <module>()
      1 fig = go.Figure()
----> 2 trace1 = go.Scatter(x=Africa_wheat_ave["Year"], y=Africa_wheat_max["yield"], mode="lines+markers", name="Africa Wheat")
      3 fig.add_trace(trace1)
      4 trace2 = go.Scatter(x=Africa_rice_ave["Year"], y=Africa_rice_max["yield"], mode="lines+markers", name="Africa Rice")
      5 fig.add_trace(trace2)

NameError: name 'Africa_wheat_max' is not defined

df_temp_metro_max =df_temp_metro.groupby(['Year'], as_index = False)['temperature'].max()
df_temp_metro_max.head()

df_temp_metro_max_2018 =df_temp_metro_max.query("Year == '2018'")
df_temp_metro_max_2017 =df_temp_metro_max.query("Year == '2017'")
df_temp_metro_max_2016 =df_temp_metro_max.query("Year == '2016'")
df_temp_metro_max_2015 =df_temp_metro_max.query("Year == '2015'")

# import plotly.graph_objects as go
# fig = go.Figure()
# trace1 = go.Scatter(x=df_temp_metro_max_2018["Months"], y=df_temp_metro_max_2018["temperature"], mode="lines+markers", name="2018")
# fig.add_trace(trace1)
# trace2 = go.Scatter(x=df_temp_metro_max_2017["Months"], y=df_temp_metro_max_2017["temperature"], mode="lines+markers", name="2017")
# fig.add_trace(trace2)
# trace3 = go.Scatter(x=df_temp_metro_max_2016["Months"], y=df_temp_metro_max_2016["temperature"], mode="lines+markers", name="2016")
# fig.add_trace(trace3)
# fig.update_layout(
#     title={
#         "text": "Max Temp anomaly ",
#         "x":0.5,
#         "xanchor": "center"
#         },
#     xaxis_title="Year",
#     yaxis_title="temp")
# fig.show()

Rice.head()

df_cropr_max= Rice.groupby(['Year'], as_index = False)['yield'].max()
df_cropw_max= Wheat.groupby(['Year'], as_index = False)['yield'].max()
df_cropm_max= Maize.groupby(['Year'], as_index = False)['yield'].max()

import plotly.graph_objects as go
from plotly.subplots import make_subplots

# Create figure with secondary y-axis
fig = make_subplots(specs=[[{"secondary_y": True}]])

# Add traces
fig.add_trace(
    go.Scatter(x=df_cropw_max["Year"], y=df_cropw_max["yield"], mode="lines+markers", name="Max Wheat"),
    secondary_y=False,
)

fig.add_trace(
    go.Scatter(x=df_cropr_max["Year"], y=df_cropr_max["yield"], mode="lines+markers", name="Max Rice"),
    secondary_y=False,
)

fig.add_trace(
    go.Scatter(x=df_cropm_max["Year"], y=df_cropm_max["yield"], mode="lines+markers", name="Max Maize"),
    secondary_y=False,
)    
fig.add_trace(
    go.Scatter(x=df_temp_metro_max["Year"], y=df_temp_metro_max["temperature"], mode="lines+markers", name="Max Temp"),
    secondary_y=True,
)

# Add figure title
fig.update_layout(
    title_text="Max crop production & Maximum Temperature"
)

# Set x-axis title
fig.update_xaxes(title_text="Year")

# Set y-axes titles
fig.update_yaxes(title_text="<b>crop production per Hectare</b> ", secondary_y=False)
fig.update_yaxes(title_text="<b>Temperature in celicious</b> ", secondary_y=True)

fig.show()

2016 is the warmest of all years .There was a pause between 1999 and 2005.¶

Merging temperature,co2 and crop data¶

df_co2.head()

df_co2.rename(columns={'CountryName' :'Area', 'year':'Year', 'Value': 'co2'}, inplace = True)

df_co2.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10234 entries, 0 to 10233
Data columns (total 4 columns):
Area           10234 non-null object
CountryCode    10234 non-null object
Year           10234 non-null object
co2            10234 non-null float64
dtypes: float64(1), object(3)
memory usage: 319.9+ KB

df_co2['Year']= df_co2.Year.astype('int64')
df_co2.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10234 entries, 0 to 10233
Data columns (total 4 columns):
Area           10234 non-null object
CountryCode    10234 non-null object
Year           10234 non-null int64
co2            10234 non-null float64
dtypes: float64(1), int64(1), object(2)
memory usage: 319.9+ KB

df_crop_temp.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 169677 entries, 0 to 218176
Data columns (total 14 columns):
Area Code_x     169677 non-null int64
Area            169677 non-null object
Months Code     169677 non-null int64
Months          169677 non-null object
Year            169677 non-null int64
temperature     169677 non-null float64
pos_temp        169677 non-null float64
Area Code_y     169677 non-null float64
Item Code       169677 non-null float64
Item            169677 non-null object
yield           169677 non-null float64
region          169677 non-null object
Country Code    169677 non-null float64
temp            169677 non-null object
dtypes: float64(6), int64(3), object(5)
memory usage: 19.4+ MB

df_crop_temp_sorted=df_crop_temp.sort_values(by=['Year'])
df_co2_sorted=df_co2.sort_values(by=['Year'])

df_crop_temp_co2  = pd.merge_asof(df_co2_sorted, df_crop_temp_sorted,
              on='Year',
              by='Area')

df_crop_temp_co2.head()

df_crop_temp_co2 = df_crop_temp_co2.dropna()

df_co2.isna().sum()

Area           0
CountryCode    0
Year           0
co2            0
dtype: int64

df_crop_temp_co2.head()

df_crop_temp_co2.region.unique()

array(['World', 'Least_Developed_Countries',
       'Upper_middle_income_economies',
       'Low_Income_Food_Deficit_Countries', 'Sub_Saharan_Africa',
       'Annex_I_countries', 'OECD', 'Asia', 'Western_Africa',
       'Latin_America_and_the_Caribbean', 'Non_Annex_I_countries',
       'High_income_economies', 'Western_Asia', 'Africa',
       'South_Asia_(exc_India)', 'Central_America', 'South_Eastern_Asia',
       'North_Africa_(exc_Sudan)', 'Small_Island_Developing_States',
       'Lower_middle_income_economies',
       'Sub_Saharan_Africa_(including_Sudan)', 'Americas',
       'Net_Food_Importing_Developing_Countries', 'European_Union',
       'Europe', 'South_America', 'Land_Locked_Developing_Countries',
       'Western_Asia_and_Northern_Africa', 'Northern_America_and_Europe',
       'Oceania_excluding_Australia_and_New_Zealand', 'Southern_Asia',
       'Southern_Europe', 'Northern_Africa',
       'Eastern_Asia_and_South_eastern_Asia', 'Low_income_economies',
       'Northern_Europe', 'Eastern_Europe', 'Eastern_Africa', 'Caribbean',
       'Western_Europe', 'Central_Asia_and_Southern_Asia',
       'Southern_Africa', 'Melanesia', 'Eastern_Asia', 'Middle_Africa',
       'Oceania', 'Australia_and_New_Zealand', 'Central_Asia',
       'East_Asia_(exc_China)'], dtype=object)

df_crop_temp_co2_reg = df_crop_temp_co2.query( "region in ['World','Asia','Africa' ]")
df_crop_temp_co2_reg.head()

Plot co2 , temperature and crop by region¶

fig = px.scatter(
    df_crop_temp_co2_reg, 
    x="temperature", 
    y="co2", 
    animation_frame="Year", 
    animation_group="Area",
    size="yield", 
    color="region", 
    hover_name="Area", 
    facet_col="region",
    size_max=45
#     range_y=[0,1000]
)
fig.show()

import plotly.express as px
fig = px.bar(df_crop_temp_co2_reg, x="region", y="co2",color='co2',
            animation_frame='Year', hover_name='Area')
fig.show()

df_crop_temp_co2.nlargest(5, ['co2'])
# df.nlargest(5, ['total exports'])

	Domain Code	Domain	Area Code	Area	Element Code	Element	Item Code	Item	Year Code	Year	Unit	Value	Flag	Flag Description
0	QC	Crops	2	Afghanistan	5510	Production	44	Barley	1961	1961	tonnes	378000.0	NaN	Official data
1	QC	Crops	2	Afghanistan	5510	Production	44	Barley	1962	1962	tonnes	378000.0	NaN	Official data
2	QC	Crops	2	Afghanistan	5510	Production	44	Barley	1963	1963	tonnes	378000.0	NaN	Official data
3	QC	Crops	2	Afghanistan	5510	Production	44	Barley	1964	1964	tonnes	380000.0	NaN	Official data
4	QC	Crops	2	Afghanistan	5510	Production	44	Barley	1965	1965	tonnes	380000.0	NaN	Official data

	Domain Code	Domain	Area Code	Area	Element Code	Element	Item Code	Item	Year Code	Year	Unit	Value	Flag	Flag Description
0	QC	Crops	2	Afghanistan	5419	Yield	44	Barley	1961	1961	hg/ha	10800.0	Fc	Calculated data
1	QC	Crops	2	Afghanistan	5419	Yield	44	Barley	1962	1962	hg/ha	10800.0	Fc	Calculated data
2	QC	Crops	2	Afghanistan	5419	Yield	44	Barley	1963	1963	hg/ha	10800.0	Fc	Calculated data
3	QC	Crops	2	Afghanistan	5419	Yield	44	Barley	1964	1964	hg/ha	10857.0	Fc	Calculated data
4	QC	Crops	2	Afghanistan	5419	Yield	44	Barley	1965	1965	hg/ha	10857.0	Fc	Calculated data

Number of variables	14
Number of observations	37322
Total Missing (%)	0.0%
Total size in memory	4.0 MiB
Average record size in memory	112.0 B

Numeric	4
Categorical	4
Boolean	0
Date	0
Text (Unique)	0
Rejected	6
Unsupported	0

Distinct count	197
Unique (%)	0.5%
Missing (%)	0.0%
Missing (n)	0